fix(core): bump stream stall watchdog default to 5 min#155
Merged
Conversation
Long agentic turns (parallel subagent dispatch, deep mid-stream planning pauses) were tripping the 90 s per-chunk idle watchdog and surfacing as "Stream stalled: no data received for 90s" even on healthy connections. Bump the default to 300 s — still catches genuine frozen connections, but gives legitimate slow-but-steady streams the headroom they need. PROTO_STREAM_STALL_TIMEOUT_MS env override unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
WalkthroughIncreases the Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/core/src/core/turn.ts`:
- Around line 45-47: STREAM_STALL_TIMEOUT_MS currently uses parseInt on an env
var without validation; after parsing the raw value for STREAM_STALL_TIMEOUT_MS,
validate it (reject NaN or values <= 0), apply a safe default of 300000 if
invalid, and clamp the parsed value to a reasonable min/max range (e.g., min
1000 ms, max something large) before assigning; locate and update the constant
definition for STREAM_STALL_TIMEOUT_MS in turn.ts so it uses the
validated/clamped numeric value instead of the raw parseInt result.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: cd97024d-d04a-4072-adc8-7d0d75e9c6f3
📒 Files selected for processing (2)
docs/reference/settings.mdpackages/core/src/core/turn.ts
Comment on lines
45
to
47
| const STREAM_STALL_TIMEOUT_MS = parseInt( | ||
| process.env['PROTO_STREAM_STALL_TIMEOUT_MS'] ?? '90000', | ||
| process.env['PROTO_STREAM_STALL_TIMEOUT_MS'] ?? '300000', | ||
| 10, |
There was a problem hiding this comment.
Harden env timeout parsing to avoid invalid watchdog values.
parseInt(process.env[...] ?? '300000', 10) accepts invalid/unsafe inputs (NaN, <= 0), which can cause immediate or undefined stall behavior. Add a bounded fallback after parsing.
Suggested patch
-const STREAM_STALL_TIMEOUT_MS = parseInt(
- process.env['PROTO_STREAM_STALL_TIMEOUT_MS'] ?? '300000',
- 10,
-);
+const parsedStreamStallTimeoutMs = Number.parseInt(
+ process.env['PROTO_STREAM_STALL_TIMEOUT_MS'] ?? '300000',
+ 10,
+);
+const STREAM_STALL_TIMEOUT_MS =
+ Number.isFinite(parsedStreamStallTimeoutMs) && parsedStreamStallTimeoutMs > 0
+ ? parsedStreamStallTimeoutMs
+ : 300_000;🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@packages/core/src/core/turn.ts` around lines 45 - 47, STREAM_STALL_TIMEOUT_MS
currently uses parseInt on an env var without validation; after parsing the raw
value for STREAM_STALL_TIMEOUT_MS, validate it (reject NaN or values <= 0),
apply a safe default of 300000 if invalid, and clamp the parsed value to a
reasonable min/max range (e.g., min 1000 ms, max something large) before
assigning; locate and update the constant definition for STREAM_STALL_TIMEOUT_MS
in turn.ts so it uses the validated/clamped numeric value instead of the raw
parseInt result.
Code Coverage Summary
CLI Package - Full Text ReportCore Package - Full Text ReportFor detailed HTML reports, please see the 'coverage-reports-22.x-ubuntu-latest' artifact from the main CI run. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Stream stalled: no data received for 90seven on healthy connections.STREAM_STALL_TIMEOUT_MSfrom90_000→300_000(5 min). Still catches genuine frozen connections, but gives slow-but-steady streams the headroom they need.PROTO_STREAM_STALL_TIMEOUT_MSenv override is unchanged — set it lower if you want tighter detection.Test plan
PROTO_STREAM_STALL_TIMEOUT_MS=2000, kill the upstream connection mid-stream, and confirmStreamStallErrorstill fires + retries.streamStall.test.tssuite passes (no test pinned to the old default).🤖 Generated with Claude Code
Summary by CodeRabbit